CN110161544B - Vehicle driving state identification method and device and storage medium - Google Patents

Vehicle driving state identification method and device and storage medium Download PDF

Info

Publication number
CN110161544B
CN110161544B CN201810338511.2A CN201810338511A CN110161544B CN 110161544 B CN110161544 B CN 110161544B CN 201810338511 A CN201810338511 A CN 201810338511A CN 110161544 B CN110161544 B CN 110161544B
Authority
CN
China
Prior art keywords
displacement direction
gps
vehicle
gps point
included angles
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201810338511.2A
Other languages
Chinese (zh)
Other versions
CN110161544A (en
Inventor
刘雨亭
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tencent Technology Shenzhen Co Ltd
Tencent Dadi Tongtu Beijing Technology Co Ltd
Original Assignee
Tencent Technology Shenzhen Co Ltd
Tencent Dadi Tongtu Beijing Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Tencent Technology Shenzhen Co Ltd, Tencent Dadi Tongtu Beijing Technology Co Ltd filed Critical Tencent Technology Shenzhen Co Ltd
Priority to CN201810338511.2A priority Critical patent/CN110161544B/en
Publication of CN110161544A publication Critical patent/CN110161544A/en
Application granted granted Critical
Publication of CN110161544B publication Critical patent/CN110161544B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/42—Determining position
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
    • G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
    • G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
    • G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
    • G01S19/52—Determining velocity

Landscapes

  • Engineering & Computer Science (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)
  • Position Fixing By Use Of Radio Waves (AREA)

Abstract

The invention relates to the technical field of driving information processing, and discloses a method and a device for identifying a vehicle driving state and a storage medium, which are used for improving the accuracy of vehicle driving state identification. The method for identifying the driving state of the vehicle comprises the following steps: obtaining a plurality of continuous GPS point data of a vehicle; determining displacement direction vectors between every two adjacent GPS points or between every two GPS points separated by a set number according to the obtained GPS point data to obtain a plurality of displacement direction vectors; determining a displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles; and determining the driving state of the vehicle according to the change characteristics of the included angles of the plurality of displacement directions in the driving process of the vehicle.

Description

Vehicle driving state identification method and device and storage medium
Technical Field
The invention relates to the technical field of driving information processing, in particular to a method and a device for identifying a driving state of a vehicle and a storage medium.
Background
With the development of social economy, the living standard of people is improved, automobiles become indispensable transportation tools for families, and the driving information processing technology is developed and applied along with the development of network technology. Research shows that the driving state of a vehicle in the process of driving a vehicle has a traffic accident indicates the possibility of the accident to a certain extent, so that the vehicle driving state recognition technology in the electronic map technology is operated to improve the driving safety of the vehicle, and the vehicle driving state recognition technology is utilized to perform early warning when the vehicle is judged to be in a dangerous state, so that the traffic accident is prevented to a certain extent.
The increase of the driving and traveling frequency of people makes the accuracy of the vehicle driving state identification in the driving information processing technology have important practical significance for preventing the occurrence of traffic accidents, so how to improve the accuracy of the vehicle driving state identification and thus the ability of preventing traffic accidents is one of the technical problems to be considered.
Disclosure of Invention
The embodiment of the invention provides a method and a device for identifying a vehicle driving state and a storage medium, which are used for improving the accuracy of identifying the vehicle driving state so as to improve the capacity of preventing traffic accidents.
In a first aspect, an embodiment of the present invention provides a method for identifying a driving state of a vehicle, including:
obtaining a plurality of continuous GPS point data of a vehicle;
determining displacement direction vectors between every two adjacent GPS points or between every two GPS points separated by a set number according to the obtained GPS point data to obtain a plurality of displacement direction vectors;
determining a displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles;
and determining the driving state of the vehicle according to the change characteristics of the included angles of the plurality of displacement directions in the driving process of the vehicle.
The vehicle driving state identification method provided by the embodiment of the invention firstly utilizes a plurality of continuous GPS point data of the vehicle to determine the displacement direction vector between every two adjacent GPS points or between every two GPS points with a set number so as to obtain a plurality of displacement direction vectors, then determining the displacement direction included angle of every two adjacent displacement direction vectors in the plurality of displacement direction vectors, thereby obtaining a plurality of displacement direction included angles, further using the change characteristics of the plurality of displacement direction included angles to determine the driving state of the vehicle, because the smaller the variation range of the included angle of the displacement direction is, the more the vehicle tends to the normal running state, and the larger the variation range of the included angle of the displacement direction is, the more the vehicle tends to the low-speed running state, even to the parking state, therefore, the vehicle driving state is determined by using the change characteristics of the displacement direction included angle, and the accuracy of vehicle driving state identification can be improved.
Optionally, determining a driving state of the vehicle according to the change characteristics of the plurality of displacement direction included angles in the driving process of the vehicle specifically includes:
determining the variation range of the included angles of the plurality of displacement directions;
determining the driving state of the vehicle according to the threshold range of the change range of the included angles of the plurality of displacement directions;
wherein each vehicle driving state corresponds to a threshold range.
In the above alternative manner, it is described that the embodiment of the present invention may specifically determine the driving state of the vehicle according to the range in which the change of the included angles of the plurality of displacement directions is located, that is, may set the threshold range corresponding to the driving state of the different vehicles as the determination criterion, and further determine the driving state of the vehicle by determining the threshold range in which the change of the included angles of the plurality of displacement directions is located.
Optionally, the determining the variation range of the included angles of the plurality of displacement directions specifically includes:
determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain a plurality of displacement direction included angle cosine values;
determining a first-order difference of cosine values of included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences;
and determining the variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences.
Above-mentioned optional mode, make full use of if the variation range of a plurality of displacement direction contained angles is little, then, by the difference of every two adjacent displacement vector contained angles in a plurality of displacement direction contained angles, the dispersion that the difference of a plurality of displacement vector contained angles that obtains shows will be lower, if the variation range of a plurality of displacement direction contained angles is big, the dispersion that the difference of a plurality of displacement vector contained angles shows will be higher, therefore, can be specifically through confirming the cosine value of every two adjacent displacement direction contained angles in a plurality of displacement direction contained angles, further through confirming the first order difference of every two adjacent displacement direction contained angle cosine values in a plurality of cosine values, and then through the discrete characteristic of a plurality of first order differences also namely the dispersion, confirm the vehicle driving state, the degree of accuracy of vehicle driving state discernment has been improved.
Optionally, determining a variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences specifically includes:
determining a variance or standard deviation of the plurality of first-order differences, wherein the variance or standard deviation represents a variation range of the plurality of displacement direction included angles.
Optionally, determining a variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences specifically includes:
performing wavelet transformation on the first-order differences to obtain a wavelet transformation result, wherein the wavelet transformation result represents the variation range of the included angles of the displacement directions; or
And performing convolution on the plurality of first-order differences to obtain a convolution result, wherein the convolution result represents the variation range of the plurality of displacement direction included angles.
Optionally, the multiple continuous GPS point data are:
setting all GPS point data acquired within a time length; or
After all the GPS point data obtained over a period of time are divided into a plurality of sample groups in chronological order, a plurality of consecutive GPS point data included in any one sample group.
Optionally, after obtaining a plurality of consecutive GPS point data of the vehicle, the method further includes:
and if the difference of the displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is determined to be smaller than a second threshold value according to the acquired GPS point data, determining that the vehicle driving state is a parking state.
Optionally, the method further includes:
when the plurality of continuous GPS point data are obtained from the GPS point data set when the GPS point data set used for ETA model training is subjected to data preprocessing, and when the vehicle driving state is determined to be a parking state, the plurality of continuous GPS point data are removed from the GPS point data set.
In the above alternative manner, it is described that the method in the embodiment of the present invention may also be applied to ETA model training, so as to remove the GPS point data corresponding to the parking state of the vehicle in the GPS point data set used for ETA model training, thereby obtaining a more accurate ETA result.
And then the vehicle is output with controllable force
In a second aspect, an embodiment of the present invention provides an apparatus for identifying a driving state of a vehicle, including:
an acquisition unit for acquiring a plurality of continuous GPS point data of a vehicle;
the first determining unit is used for determining displacement direction vectors between every two adjacent GPS points or between every two GPS points which are separated by a set number according to the acquired GPS point data to obtain a plurality of displacement direction vectors;
the second determining unit is used for determining a displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles;
and the third determining unit is used for determining the driving state of the vehicle according to the change characteristics of the plurality of displacement direction included angles in the driving process of the vehicle.
Optionally, the third determining unit is further configured to:
determining the variation range of the included angles of the plurality of displacement directions;
and determining the vehicle driving states according to the threshold value ranges of the variation ranges of the plurality of displacement direction included angles, wherein each vehicle driving state corresponds to one threshold value range.
Optionally, the third determining unit is further configured to:
determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain a plurality of displacement direction included angle cosine values;
determining a first-order difference of cosine values of included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences;
and determining the variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences.
Optionally, the third determining unit is further configured to:
determining a variance or standard deviation of the plurality of first-order differences, wherein the variance or standard deviation represents a variation range of the plurality of displacement direction included angles.
Optionally, the third determining unit is further configured to:
performing wavelet transformation on the first-order differences to obtain a wavelet transformation result, wherein the wavelet transformation result represents the variation range of the included angles of the displacement directions; or
And performing convolution on the plurality of first-order differences to obtain a convolution result, wherein the convolution result represents the variation range of the plurality of displacement direction included angles.
Optionally, the multiple continuous GPS point data are:
setting all GPS point data acquired within a time length; or
After all the GPS point data obtained over a period of time are divided into a plurality of sample groups in chronological order, a plurality of consecutive GPS point data included in any one sample group.
Optionally, the third determining unit is further configured to:
and if the difference of the displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is determined to be smaller than a second threshold value according to the acquired GPS point data, determining that the vehicle driving state is a parking state.
Optionally, the third determining unit is further configured to:
when the plurality of continuous GPS point data are obtained from the GPS point data set when the GPS point data set used for ETA model training is subjected to data preprocessing, and when the vehicle driving state is determined to be a parking state, the plurality of continuous GPS point data are removed from the GPS point data set.
In a fourth aspect, an embodiment of the present invention provides a computing apparatus, including at least one processor, and at least one memory, where the memory stores a computer program, and when the program is executed by the processor, the processor is caused to perform the steps of the method according to the first aspect.
In a fifth aspect, an embodiment of the present invention provides a computer-readable medium, which stores a computer program executable by a terminal device, and when the program runs on the terminal device, the program causes the terminal device to execute the steps of the method according to the first aspect.
The method for identifying the vehicle driving state provided by the embodiment of the invention fully considers that if certain GPS reporting moments drift within a period of time, the reported GPS point data is inaccurate, the displacement mode between every two GPS points is large in the normal driving state, the influence of the inaccurate GPS point data on the large displacement mode is small, and the variation range of the included angle of the whole displacement direction within the period of time is still within a small range; and the displacement mode between every two GPS points is small when the vehicle runs at low speed or is stopped, the influence of inaccurate GPS point data on the small displacement mode is large, and further the change range of the whole displacement direction included angle in the period is large, so that the driving state of the vehicle is determined according to the change characteristics of a plurality of displacement direction included angles in the running process of the vehicle, and the identification accuracy of the driving state of the vehicle can be improved.
Meanwhile, the change characteristics of the included angles of the plurality of displacement directions in the driving process of the vehicle are utilized, and even if one or more inaccurate GPS point data exist in the obtained plurality of GPS point data, the overall change characteristics of the included angles of the plurality of displacement directions cannot be influenced, so that the data noise and abnormal values are relatively strong in inclusion, and the application range of the scheme is also expanded.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
FIG. 1 is a schematic diagram of a vehicle and satellite communication disconnection provided by an embodiment of the present invention;
fig. 2a is a schematic view of an application scenario provided in an embodiment of the present invention;
fig. 2b is a schematic diagram of another application scenario provided in the embodiment of the present invention;
fig. 3 is a flowchart of a vehicle driving state identification method according to an embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating a method for determining a displacement direction vector according to an embodiment of the present invention;
FIG. 5 is a schematic diagram of another embodiment of the present invention for determining a displacement direction vector;
FIG. 6 is a schematic diagram illustrating an exemplary method for determining an included angle between vectors of displacement directions;
FIG. 7 is a flow chart of another method for identifying a driving state of a vehicle according to an embodiment of the present invention;
fig. 8 is a schematic view of a vehicle driving state recognition apparatus according to an embodiment of the present invention;
fig. 9 is a schematic diagram of a computer device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the technical solutions of the present invention. All other embodiments obtained by a person skilled in the art without any inventive work based on the embodiments described in the present application are within the scope of the protection of the technical solution of the present invention.
For convenience of understanding, terms referred to in the embodiments of the present invention are explained below.
The driving state of the vehicle: the present invention relates to a division of a vehicle state according to a running speed of the vehicle, and can be generally divided into a normal running state, a low speed running state, and a parking state, for example, the normal running state is a state in which the vehicle runs at a speed not lower than a first speed, the low speed running state is a state in which the vehicle runs at a speed lower than the first speed, and the parking state is a state in which the vehicle speed is 0 or tends to 0, wherein the first speed can be set according to actual needs, such as 10km/h, 15km/h, and the like.
GPS point: the coordinate position of the vehicle at the GPS sampling time (also called GPS reporting time).
ETA: estimated Time of Arrival, i.e., the Estimated Time of Arrival, the ETA model is an algorithmic model used to estimate the ETA value.
In the technical field of driving information processing, driving information can be applied to scenes such as navigation, automatic driving, electronic maps and the like, and GPS data in the driving information is data information describing that vehicles are most main and most original. The common data format for GPS data contains the following fields: GPS latitude and longitude data, GPS time stamps, GPS instantaneous speed, GPS altitude, etc., by which the state of motion of the vehicle can be described.
At present, the method for judging the driving state of the vehicle by using the GPS data mainly comprises two schemes, wherein the first scheme is mainly to judge the driving state of the vehicle by using the GPS instantaneous speed in the GPS data; the second scheme mainly uses the magnitude of the modulus of the displacement vector of the GPS point to judge the driving state of the vehicle, however, in the specific practical process, the inventor finds that the first scheme has a large dependence on the reliability of the instantaneous speed of the GPS point, and when the GPS position of the vehicle drifts during the driving process, the reliability of the instantaneous speed of the GPS point is low, so that the driving state is not accurately identified.
However, when the GPS position is in a drift state, for example, as shown in fig. 1, the vehicle 10 is blocked by the building 11 during normal driving, and communication between the GPS unit in the vehicle 10 and the satellite 12 is disconnected, so that the GPS unit in the vehicle 10 needs to indirectly communicate with the satellite 12 through the nearby base station 13, and further the satellite 12 mistakes the position of the nearby base station 13 as the current position of the vehicle 10, and the problem that the building 11 blocking communication between the vehicle and the satellite is dense is more serious, and thus the server 14 misjudges the driving state of the vehicle 10, so that the second scheme also has the problem that the driving state identification is not accurate enough.
Therefore, the inventor considers that the variation range of the displacement direction included angle formed by adjacent GPS points is small in the normal driving state of the vehicle, even if the reported GPS points drift at certain GPS reporting moments within a period of time, the reported GPS point data is inaccurate, the displacement mode between every two GPS points is large in the normal driving state, the influence of the inaccurate GPS point data on a large displacement mode is small, and therefore the fluctuation of the whole displacement direction included angle within a period of time is small, namely the variation range of the displacement direction included angle is still within a small range.
When the vehicle is in a low-speed driving or stopping state, the variation range of the displacement direction included angle formed by adjacent GPS points is large, if the reported time of some GPS points in a period of time has a drift phenomenon, the reported GPS point data is inaccurate, the displacement mode between every two GPS points in the low-speed driving or stopping state is small, the influence of the inaccurate GPS point data on the small displacement mode is large, and further the fluctuation of the whole displacement direction included angle in a period of time is larger. Therefore, the change characteristics of the plurality of displacement direction included angles in the driving process of the vehicle are adopted to determine the driving state of the vehicle more accurately.
Based on this, the embodiment of the present invention provides a method for identifying a driving state of a vehicle, which may first obtain a plurality of continuous GPS point data of the vehicle, and then determine, according to the obtained GPS point data, a displacement direction vector between every two adjacent GPS points or between every two GPS points separated by a set number, and then determine a displacement direction included angle between every two adjacent displacement direction vectors, and further determine the driving state of the vehicle according to a change characteristic of a plurality of displacement direction included angles of the vehicle in a driving process.
The method for identifying the driving state of the vehicle in the embodiment of the present invention may be applied to an application scenario as shown in fig. 2a, where the application scenario includes a satellite 21, a base station 22 and a server 23, where the server 23 may be a server that needs GPS data to perform related services, or may be a server cluster or a cloud computing center that is composed of a plurality of servers, the vehicle 20 travels on a road, the satellite 21 directly communicates with a positioning unit in the vehicle 20, the positioning unit in the vehicle 20 may be a GPS positioning chip, or may be any mobile device with a positioning function, such as a mobile phone of a driver, an IPAD, etc., the vehicle 20 directly communicates with the satellite 21 through the positioning unit in the vehicle 20, the vehicle 20 may collect the GPS point data of the vehicle during traveling in real time, and the vehicle 20 may also send the GPS point data collected in real time during traveling to the server 23 through the base station 22 at the time reported by the GPS, thereby enabling the server 23 to obtain the GPS point data of the vehicle 20 during running in real time.
The method for identifying the driving state of the vehicle in the embodiment of the present invention may also be applied to an application scenario as shown in fig. 2b, where the application scenario includes a satellite 31, a roadside communication device 32 and a server 33, the vehicle 30 runs on a road, the satellite 31 directly communicates with a positioning unit in the vehicle 30, so that the vehicle 30 can collect the GPS point data of the vehicle during running in real time, the vehicle 30 may also send the GPS point data collected in real time during running to the server 33 through the roadside communication device 32 at the GPS reporting time, and the server 33 obtains the GPS point data of the vehicle 30 during running in real time.
It should be noted that the above-mentioned application scenarios are only presented to facilitate understanding of the spirit and principles of the present invention, and the present invention is not limited in this respect. Rather, embodiments of the present invention may be applied in any scenario where applicable.
The following describes a method for identifying road conditions according to an embodiment of the present invention with reference to an application scenario shown in fig. 2 a.
As shown in fig. 3, a method for identifying a driving state of a vehicle according to an embodiment of the present invention includes:
step S101: a plurality of successive GPS point data for the vehicle is acquired.
In practical application, a GPS unit in a vehicle reports GPS data of a position of the vehicle at a current time in real time at a GPS reporting time during a running process of the vehicle, in an embodiment of the present invention, a set time length may be preset, for example, the set time length is 30 seconds, or the set time length is 1 minute, or the set time length is 5 minutes, and the like, and then a server may collect all GPS data reported by the GPS unit of the vehicle within the set time length, generally, all GPS data reported within the set time length includes data of a plurality of consecutive GPS points, and the data of each GPS point includes a set of coordinate information of each GPS point, that is, longitude and latitude data, and, of course, a GPS timestamp, that is, data of a GPS reporting time, a GPS instantaneous speed, a GPS altitude, and the like, which are listed differently.
In a specific practical process, a GPS reporting period of a GPS unit in a vehicle may be set according to actual needs, for example, the GPS reporting period is set to 1 second, if the set time length is 1 minute, the data of 60 consecutive GPS points are included in the 1 minute, and if the GPS reporting period is set to 2 seconds, the data of 30 consecutive GPS points are included in the 1 minute if the set time length is 1 minute.
In the embodiment of the present invention, specifically, taking a GPS reporting period of 2 seconds as an example, then, when the set time length is 20 seconds, all GPS data reported by a GPS unit of a vehicle acquired by a server includes data of 10 consecutive GPS points; when the set time length is 1 minute, all the GPS data reported by the GPS unit of the vehicle, which is acquired by the server, comprises data of 30 continuous GPS points; when the set time length is 4 minutes, all the GPS data reported by the GPS unit of the vehicle acquired by the server include data of 120 consecutive GPS points, which is not listed here.
Step S102: and determining displacement direction vectors between every two adjacent GPS points or between every two GPS points separated by a set number according to the obtained GPS point data to obtain a plurality of displacement direction vectors.
In the embodiment of the present invention, after acquiring data of a plurality of consecutive GPS points within a set time length, the server may determine, according to the data of the plurality of consecutive GPS points, a displacement direction vector between every two adjacent GPS points in the plurality of consecutive GPS points, or may determine a displacement direction vector between every two GPS points spaced by a set number in the plurality of consecutive GPS points.
For example, when the set time length is 20 seconds, the server acquires data of 10 consecutive GPS points, which are referred to as GPS point 1, GPS point 2, GPS point 3, GPS point 4, GPS point 5, GPS point 6, GPS point 7, GPS point 8, GPS point 9, and GPS point 10, respectively, for convenience of description, and the server can determine a displacement direction vector between every two adjacent GPS points among the 10 GPS points.
As shown in fig. 4, for the server to determine the displacement direction vector according to each adjacent two GPS points based on the data of the above 10 GPS points, so as to obtain a schematic diagram of 9 displacement direction vectors, due to space limitation, fig. 4 only illustrates that the GPS point 1, the GPS point 2, the GPS point 3, the GPS point 4, the GPS point 5, and the GPS point 6 of the 10 GPS points determine the displacement direction vector according to each adjacent two GPS points, and reference may be made to fig. 4 in a manner that each adjacent two GPS points of the remaining GPS points determine the displacement direction vector.
In fig. 4, GPS point 1, GPS point 2, GPS point 3, GPS point 4, GPS point 5, and GPS point 6 are 6 GPS points that are adjacent in this order, and it is assumed here that the coordinate of GPS point 1 is (x)1,y1) The coordinates of GPS point 2 are (x)2,y2) The coordinates of the GPS point 3 are (x)3,y3) The coordinates of the GPS point 4 are (x)4,y4) The coordinates of the GPS point 5 are (x)5,y5) The coordinates of the GPS point 6 are (x)6,y6) Then, the displacement direction vector V1 between GPS point 1 and GPS point 2 is: v. of1＝(x2-x1,y2-y1) (ii) a The displacement direction vector V2 between GPS point 2 and GPS point 3 is: v. of2＝(x3-x2,y3-y2) (ii) a Displacement direction vector between GPS point 3 and GPS point 4V3 is then: v. of3＝(x4-x3,y4-y3) (ii) a The displacement direction vector V4 between GPS point 4 and GPS point 5 is: v. of4＝(x5-x4,y5-y4) (ii) a The displacement direction vector V5 between GPS point 5 and GPS point 6 is: v. of5＝(x6-x5,y6-y7) By analogy, another 4 displacement direction vectors can be obtained, that is, the displacement direction vector V6 between the GPS point 6 and the GPS point 7, the displacement direction vector V7 between the GPS point 7 and the GPS point 8, the displacement direction vector V8 between the GPS point 8 and the GPS point 9, and the displacement direction vector V9 between the GPS point 9 and the GPS point 10.
In a specific practical process, if the set time length is long and the number of GPS points collected by the server is large, in order to improve the calculation efficiency, the displacement direction vector between every two GPS points separated by the set number in the plurality of consecutive GPS points may be determined.
For example, when the set time length is 1 minute, the server acquires data of 30 consecutive GPS points, and for convenience of description, the 30 GPS points are respectively referred to as GPS point 1, GPS point 2, GPS point 3, GPS point 4, GPS point 5, GPS point 6, GPS point 7, GPS point 8, GPS point 9, GPS point 10, GPS point 11, GPS point 12, GPS point 13, GPS point 14, GPS point 15, GPS point 16, GPS point 17, GPS point 18, GPS point 19, GPS point 20, GPS point 21, GPS point 22, GPS point 23, GPS point 24, GPS point 25, GPS point 26, GPS point 27, GPS point 28, GPS point 29, and GPS point 30.
As shown in fig. 5, 15 GPS points 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, and 29 are selected from the data of 30 GPS points at a sampling interval of 1 GPS point.
Then, the displacement direction vector V1 between the GPS point 1 and the GPS point 3, the displacement direction vector V2 between the GPS point 3 and the GPS point 5, and the displacement direction vector V3 between the GPS point 5 and the GPS point 7 are sequentially determined until the displacement direction vector V14 between the GPS point 27 and the GPS point 29, that is, the server determines the displacement direction vector between each two GPS points every 1 GPS point apart according to the data of 30 GPS points, and due to space limitation, fig. 5 only illustrates the GPS point 1, the GPS point 2, the GPS point 3, the GPS point 4, the GPS point 5, the GPS point 6, and the GPS point 7.
In practical application, the server may further select 10 GPS points from the data of 30 GPS points according to sampling intervals of 2 GPS points, and then determine a displacement direction vector between every two adjacent GPS points in the selected 10 GPS points, that is, the server determines a displacement direction vector between every two GPS points every 2 GPS points apart according to the data of 30 GPS points, and of course, in a specific practical process, specific values of the set number every 2 GPS points apart may be set according to actual needs, which is not listed herein.
In the embodiment of the present invention, as shown in fig. 4, specifically, when the set time length is 20 seconds, the server acquires data of 10 consecutive GPS points, which are divided into GPS point 1, GPS point 2, GPS point 3, GPS point 4, GPS point 5, GPS point 6, GPS point 7, GPS point 8, GPS point 9, and GPS point 10, and the server determines a displacement direction vector for each adjacent two GPS points, thereby acquiring 9 displacement direction vectors.
If it is assumed that the longitude and latitude (referred to as coordinate information) of the acquired 10 GPS points are shown in table 1:
table 1:
latitude and longitude (coordinate)
GPS Point 1 [113.834026,22.886551]
GPS Point 2 [113.834024,22.886548]
GPS Point 3 [113.834010,22.886550]
GPS Point 4 [113.833980,22.886578]
GPS Point 5 [113.833980,22.886620]
GPS Point 6 [113.834000,22.886673]
GPS Point 7 [113.834044,22.886779]
GPS point 8 [113.834094,22.886944]
GPS point 9 [113.834141,22.887098]
GPS point 10 [113.834213,22.887288]
Then, according to the longitude and latitude of 10 GPS points shown in table 1, the server determines the displacement direction vector according to each two adjacent GPS points, and then may determine to obtain 9 displacement direction vectors, where the 9 displacement direction vectors are shown in table 2:
table 2:
displacement direction vector V1 of GPS point 1 and GPS point 2 [-0.000002,-0.000003]
Displacement direction vector V2 of GPS point 2 and GPS point 3 [-0.000014,0.000002]
Displacement direction vector V3 of GPS point 3 and GPS point 4 [-0.000030,0.000028]
Displacement direction vector V4 of GPS point 4 and GPS point 5 [0.000000,0.000042]
Displacement direction vector V5 of GPS point 5 and GPS point 6 [0.000020,0.000053]
Displacement direction vector V6 of GPS point 6 and GPS point 7 [0.000044,0.000106]
Displacement direction vector V7 of GPS point 7 and GPS point 8 [0.000050,0.000165]
Displacement direction vector V8 of GPS point 8 and GPS point 9 [0.000047,0.000154]
Displacement direction vector V9 of GPS point 9 and GPS point 10 [0.000072,0.000190]
Step S103: and determining the displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles.
Referring to fig. 6, in the embodiment of the present invention, after the server obtains 9 displacement direction vectors shown in table 2, an included angle between every two adjacent displacement direction vectors can be determined according to the obtained 9 displacement direction vectors, so as to obtain 8 displacement direction included angles, for convenience of description, the obtained 8 displacement direction included angles are sequentially referred to as an included angle 1, an included angle 2, an included angle 3, an included angle 4, an included angle 5, an included angle 6, an included angle 7, and an included angle 8, and due to space limitations, fig. 6 only illustrates an included angle 1 between a displacement direction vector V1 and a displacement direction vector V2, an included angle 2 between a displacement direction vector V2 and a displacement direction vector V3, an included angle 3 between a displacement direction vector V3 and a displacement direction vector V4, and an included angle 4 between a displacement direction vector V4 and a displacement direction vector V5.
Step S104: and determining the driving state of the vehicle according to the change characteristics of the included angles of the plurality of displacement directions of the vehicle in the driving process.
In the embodiment of the invention, the server determines the included angle of every two adjacent displacement direction vectors in the 9 displacement direction vectors according to the obtained 9 displacement direction vectors, so that after the 8 displacement direction included angles from the included angle 1 to the included angle 8 are obtained, the driving state of the vehicle can be determined according to the change characteristics of the 8 displacement direction included angles.
In the step S104, the driving state of the vehicle is determined according to the variation characteristics of the plurality of displacement direction included angles during the driving process of the vehicle, and there may be a plurality of manners, for example, the driving state of the vehicle may be determined according to a preset range where the variation ranges of the plurality of displacement direction included angles are located, where each driving state of the vehicle corresponds to a threshold range, and the smaller the variation range of the plurality of displacement direction included angles is, the faster the vehicle is driven, and the larger the variation range of the plurality of displacement direction included angles is, the faster the vehicle is driven, and even the vehicle is in a parking state, for example, two thresholds T1 and T2 are set, and T2 is greater than T1, and if the variation ranges of the plurality of displacement direction included angles are less than T1, the driving state of the vehicle is determined to be the normal driving state; if the variation range of the included angles of the plurality of displacement directions is larger than or equal to T1 and smaller than T2, determining that the driving state of the vehicle is a low-speed driving state; and if the change ranges of the plurality of displacement direction included angles are larger than or equal to T2, determining that the vehicle driving state is a parking state.
For example, the cosine value or the sine value of each of the plurality of displacement direction included angles may be sequentially obtained, so as to obtain a plurality of cosine values or a plurality of sine values, then a first-order difference between every two adjacent cosine values of the plurality of cosine values may be sequentially obtained, or a first-order difference between every two adjacent sine values of the plurality of sine values may be sequentially obtained, and then a variance or a standard difference of the first-order difference may be used to determine a change of the plurality of displacement direction included angles.
The process is shown in fig. 7, and specifically includes:
step S201: and determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain the cosine values of the plurality of displacement direction included angles.
Step S202: and determining a first-order difference of the cosine values of the included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences.
Step S203: a variance or standard deviation of the plurality of first order differences is determined.
Step S204: setting threshold values T1 and T2, wherein T2 is greater than T1, determining the threshold range of variance or standard deviation, and if the variance or standard deviation is less than T1, executing step S205; if the variance or standard deviation is greater than or equal to T1 and less than T2, executing step S206; if the variance or standard deviation is greater than or equal to T2, step S207 is executed.
Step S205: and determining that the vehicle is in a normal driving state.
Step S206: and determining that the vehicle is in a low-speed running state.
Step S207: the vehicle is determined to be in a parked state.
Wherein the normal running state is a state in which the vehicle runs at a speed not lower than a first speed; the low-speed running state is a state in which the vehicle runs at a speed lower than the first speed, and the stopped state is a state in which the vehicle runs at a speed close to 0 or equal to 0.
In the embodiment of the present invention, the threshold values T1 and T2 in step S204 may be set according to a long-term and numerous test results, where T2 is greater than T1, and as a result, it is assumed that T1 takes a value of 0.15 and T2 takes a value of 0.25, so that after the server obtains 8 displacement direction included angles, namely, included angles 1 to 8, the cosine value of each included angle in included angles 1 to 8 may be sequentially obtained, so as to obtain 28 cosine values, and the obtained 28 cosine values are shown in table 3:
table 3:
cosine value
V1 and V2 0.4314554963498936
V2 and V3 0.8202021650533098
V3 and V4 0.6823182502489656
V4 and V5 0.935601718908528
V5 and V6 0.9994682153770595
V6 and V7 0.9950821216551627
V7 and V8 0.9999980372940752
V8 and V9 0.9978220618563701
In table 3, V1 and V2 represent cosine values of an included angle 1 between the displacement direction vector V1 and the displacement direction vector V2; v2 and V3 represent cosine values of an included angle 2 between the displacement direction vector V2 and the displacement direction vector V3; v3 and V4 represent cosine values of an included angle 3 between a displacement direction vector V3 and a displacement direction vector V4; v4 and V5 represent cosine values of an included angle 4 between the displacement direction vector V4 and the displacement direction vector V5; v5 and V6 represent cosine values of an included angle 5 between the displacement direction vector V5 and the displacement direction vector V6; v6 and V7 represent cosine values of an included angle 6 between the displacement direction vector V6 and the displacement direction vector V7; v7 and V8 represent cosine values of an included angle 7 between a displacement direction vector V7 and a displacement direction vector V8; v8 and V9 represent cosine values of an angle 8 between displacement direction vector V8 and displacement direction vector V9.
After the cosine values of 8 included angles shown in table 3 are obtained, the first order difference of every two adjacent cosine values in the 8 cosine values can be sequentially solved, so that 7 first order differences are obtained, the variation ranges of the included angles in the multiple displacement directions are determined according to the discrete characteristics of the 7 first order differences, and the obtained 7 first order differences are shown in table 4:
table 4:
first order difference between angle 1 and angle 2 0.043194074300379574
First order difference between angle 2 and angle 3 -0.01532043497826046
First order difference between angle 3 and angle 4 0.028142607628840258
First order difference between angle 4 and angle 5 0.0070962773853924
First order difference between angle 5 and angle 6 -0.0004873437468774222
First order difference between angle 6 and angle 7 0.0005462128487680524
First order difference between angle 7 and angle 8 -0.000241775048633899
In a specific practical process, there are various ways to obtain the discrete features of the plurality of first-order differences, for example, as in step S203, the variance or standard deviation of the obtained 7 first-order differences may be obtained, where both the variance and standard deviation are the discrete features reflecting the 7 first-order differences, for example, the wavelet transform result may be obtained by performing wavelet transform on the 7 first-order differences, and the wavelet transform result is also the discrete features reflecting the plurality of first-order differences, or as well, the convolution transform result may be obtained by performing convolution transform on the 7 first-order differences, and the convolution transform result is also the discrete features reflecting the plurality of first-order differences.
In the embodiment of the present invention, specifically taking the determination of the standard deviation of 7 first-order differences as an example, the standard deviation D obtained by calculation according to the 27 first-order differences shown in table 4 is: 0.018430052198914779, it is assumed here that, as shown in table 5, when D is less than a threshold value T1, the variation range indicating the plurality of displacement direction vectors is small, and the driving state of the vehicle is determined to be a normal driving state; when D is greater than or equal to a threshold value T1 and smaller than a threshold value T2, representing that the variation ranges of the multiple displacement direction vectors are large, and determining that the driving state of the vehicle is a low-speed driving state; when D is greater than or equal to a threshold value T2, representing that the variation range of a plurality of displacement direction vectors is large, determining that the driving state of the vehicle is a parking state:
table 5:
D＜T1 T1≤D＜T2 T2≤D
normal driving state Low speed driving state Parking state
In the embodiment of the invention, the value of T1 is 0.15, the value of T2 is 0.25, and the calculated standard deviation D is as follows: 0.018430052198914779, which is smaller than 0.15, therefore, the driving state of the vehicle is determined to be the normal driving state, but in practical application, there may be a plurality of continuous GPS point data collected according to a certain time length, and the driving state of the vehicle is determined to be the low speed driving state or the parking state by the above method, for example, if the server acquires data of 10 continuous GPS points within 20 seconds of the set time length, as shown in table 6:
table 6:
latitude and longitude (coordinate)
GPS Point 1 [114.145233,22.745547]
GPS Point 2 [114.145234,22.745548]
GPS Point 3 [114.145235,22.745546]
GPS Point 4 [114.145236,22.745544]
GPS Point 5 [114.145055,22.745434]
GPS Point 6 [114.145052,22.745412]
GPS Point 7 [114.144978,22.745339]
GPS point 8 [114.144917,22.745300]
GPS point 9 [114.144856,22.745260]
GPS point 10 [114.144792,22.745219]
Then, according to the longitude and latitude of 10 consecutive GPS points shown in table 6, the displacement direction vector between each two adjacent GPS points is determined, so as to obtain 9 displacement direction vectors, and these 9 displacement direction vectors are sequentially: [0.000001,0.000001], [0.000001, -0.000002], [0.000001, -0.000002], [ -0.000181, -0.000110], [ -0.000003, -0.000022], [ -0.000074, -0.000073], [ -0.000061, -0.000039], [ -0.000061, -0.000040], [ -0.000064, -0.000041], determining an angle of each adjacent two displacement direction vectors according to the 9 displacement direction vectors to obtain 8 angles, and then obtaining cosine values of the 8 angles to obtain 8 cosine values, wherein the 8 cosine values are sequentially: 0.31622776837611805, 1.0000000000000002, 0.08234649853650869, 0.6300481149706577, 0.7920276550471359, 0.9780834803927725, 0.9999332956929929, 0.9999433772832513, and then obtaining a first difference between every two adjacent cosine values of the 8 cosine values, thereby obtaining 7 first differences, which are: 0.4387425894587061, -0.3058845004878305, 0.1825672054780497, 0.05399318002549273, 0.06201860844854553, 0.007283271766740151, 0.0000033605300861, the standard deviation D obtained from the above 7 first order difference calculations: 0.20657370216176699, as can be seen from table 6 above, the calculated standard deviation D is greater than T1, i.e., 0.15, and less than T2, i.e., 0.25, and therefore, it is determined that the driving state of the vehicle is a low-speed driving state.
For example, if the server acquires data of 10 consecutive GPS points within a set time period of 20 seconds, as shown in table 7:
table 7:
latitude and longitude (coordinate)
GPS Point 1 [114.141728,22.744347]
GPS Point 2 [114.141731,22.744347]
GPS Point 3 [114.141730,22.744347]
GPS Point 4 [114.141732,22.744348]
GPS Point 5 [114.141731,22.744347]
GPS Point 6 [114.141731,22.744347],
GPS Point 7 [114.141732,22.744347]
GPS point 8 [114.141732,22.744347]
GPS point 9 [114.141732,22.744347]
GPS point 10 [114.141731,22.744347]
Then, according to the longitude and latitude of 10 consecutive GPS points shown in table 7, the displacement direction vector between each two adjacent GPS points is determined, so as to obtain 9 displacement direction vectors, and these 9 displacement direction vectors are sequentially: [0.000003,0.000000]，[-0.000001,0.000000]，[0.000002,0.000001]，[-0.000001,-0.000001]，[0.000000,0.000000]，[0.000001,0.000000]，[0.000000,0.000000]，[0.000000,0.000000]，[-0.000001,0.000000]In the case where the 9 displacement direction vectors are 0, the angles between the 0 displacement direction vector and the other displacement direction vectors adjacent to the 0 displacement direction vector are difficult to calculate, and therefore, in this case, the cosine of the angle between the 0 displacement direction vector and the other displacement direction vectors adjacent to the 0 displacement direction vector may be assigned to-1nWhere n is the count of the same GPS coordinate. Doing so at first can solve the unable problem of calculating of same GPS coordinate, secondly, can be with the contained angle cosine first-order difference maximize when parkking, consequently, according to above-mentioned 9 displacement direction vectors, confirm the contained angle of every two adjacent displacement direction vectors to obtain 8 contained angles, the cosine value of these 8 contained angles does in proper order: 1, -0.894427,0.9486833, -1, -1,1, -1,1.
Then, according to the cosine values of the 8 included angles, a first-order difference of each adjacent cosine value is determined, so that 7 first-order differences are obtained, namely-1.894427, 1.8431103, -1.9486833, 0, 2, -2 and 2. Standard deviation D obtained from the above 7 first order difference calculations: 1.8040935927572359, it can be seen from table 6 that the standard deviation D obtained by calculation is greater than T2, that is, 0.25, and therefore, the driving state of the vehicle is determined to be the stopped state.
Optionally, after obtaining a plurality of consecutive GPS point data of the vehicle, the method further includes:
and if the difference of the displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is determined to be smaller than a second threshold value according to the acquired GPS point data, determining that the driving state of the vehicle is a parking state.
In the embodiment of the present invention, after acquiring multiple continuous GPS point data within a certain time length, the server may determine, according to the GPS point data, whether a difference between displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is smaller than a second threshold, where the second threshold may be set according to an actual situation, and the second threshold is used to determine whether the difference between the displacement coordinates of the GPS points matches a difference between the displacement coordinates of the GPS points in the parking state, where it is assumed that the second threshold is 0.00001, and data of 10 continuous GPS points shown in table 7 is taken as an example.
The server may first determine a difference between the displacement coordinates of any two adjacent GPS points of 10 consecutive GPS points shown in table 7, compare the difference between the displacement coordinates of the any two adjacent GPS points with a second threshold, and determine that the driving state of the vehicle is the parking state if the difference between the displacement coordinates of each two adjacent GPS points is smaller than the second threshold; alternatively, the difference between the displacement coordinates of every two adjacent GPS points of 10 consecutive GPS points is determined, a plurality of differences between the displacement coordinates are obtained in total, and if the difference between most of the plurality of differences between the displacement coordinates exceeds 50% (or 60%, or 70%) and is less than the second threshold value, the driving state of the vehicle is determined to be the stopped state.
In the embodiment of the present invention, for example, the difference between the displacement coordinates of each two adjacent GPS points of 10 consecutive GPS points is obtained, and if the difference between more than 5 displacement coordinates among the differences between 9 displacement coordinates is greater than the second threshold, the driving state of the vehicle is determined as the parking state, then, as can be seen from table 7, the difference between more than 5 displacement coordinates among the differences between each two adjacent GPS points of the GPS points in table 7 is greater than the second threshold, and therefore, the driving state of the vehicle is determined as the parking state.
Optionally, in the embodiment of the present invention, the multiple continuous GPS point data obtained in step S101 may specifically be: after all the GPS point data obtained over a period of time are divided into a plurality of sample groups in chronological order, a plurality of consecutive GPS point data included in any one sample group.
In practical application, when the server acquires data of a plurality of continuous GPS points over a long period of time, for example, the server acquires data of 120 continuous GPS points over 4 minutes, after obtaining a plurality of displacement direction included angles of the 120 continuous GPS points according to the above, the plurality of displacement direction included angles may be divided into a plurality of groups according to a preset time length, and then the driving state of the vehicle in the time period corresponding to each sample group is determined according to the change characteristic of the displacement direction included angle in each sample group.
For example, the server acquires 150 consecutive GPS points within 5 minutes, 149 displacement direction vectors can be obtained according to the above method, according to 149 displacement direction vectors, every two adjacent displacement direction vectors form an included angle, thereby obtaining 148 included angles, and according to a first order difference between every two adjacent included angles in the 148 included angles, thus, after 147 first-order differences are obtained, the 147 first-order differences may be further divided into 30 time windows according to a preset time duration, for example, 10 seconds, 49 first-order differences included in each time window, and the 49 first-order differences in each time window are grouped into one sample, and for convenience of description, the 30 time windows are respectively referred to as time window 1, time window 2 … … time window 30, then, calculating 49 first-order differences in the time window 1 to obtain a standard deviation D1, and determining the vehicle driving state of the time period corresponding to the time window 1 according to the standard deviation D1; and obtaining a standard deviation D2 according to 49 first-order difference calculations in the time window 2, determining the vehicle driving state … … of the time window 2 corresponding to the time period according to the standard deviation D2 until obtaining a standard deviation D30 according to 49 first-order difference calculations in the time window 30, and determining the vehicle driving state of the time window 30 corresponding to the time period according to the standard deviation D30.
Therefore, the method for identifying the vehicle driving state in the embodiment of the invention fully considers that if certain GPS reporting moments drift within a period of time, the reported GPS point data is inaccurate, the displacement mode between every two GPS points is large in the normal driving state, the influence of the inaccurate GPS point data on the large displacement mode is small, and the variation range of the whole displacement direction included angle within the period of time is still within a small range; the displacement mode between every two GPS points is small in the low-speed running or stopping state of the vehicle, the influence of inaccurate GPS point data on the small displacement mode is large, and further the change range of the whole displacement direction included angle is large in the period of time, therefore, the driving state of the vehicle is determined according to the change characteristics of a plurality of displacement direction included angles in the running process of the vehicle, the identification accuracy of the driving state of the vehicle can be improved, meanwhile, because the change characteristics of a plurality of displacement direction included angles in the running process of the vehicle are utilized, even if one or a plurality of inaccurate GPS point data exist in the obtained plurality of GPS point data, the whole change characteristics of the plurality of displacement direction included angles cannot be influenced, therefore, the invention has strong inclusion of data noise and abnormal values, and the application range of the scheme is also increased.
In addition, after a plurality of displacement direction vector included angles are obtained according to a plurality of continuous GPS point data, the plurality of displacement direction vector included angles can be divided into a plurality of time windows according to the preset time length, and the vehicle driving state of the time period corresponding to each time window is determined according to the change characteristics of the plurality of displacement direction vector included angles in each time window, so that the time length of the vehicle in each driving state can be output in a controllable granularity.
Optionally, the method of the present invention further includes: when the plurality of continuous GPS point data are obtained from the GPS point data set when the data preprocessing is performed on the GPS point data set used for the ETA model training of the estimated arrival time, the plurality of continuous GPS point data are removed from the GPS point data set when the driving state of the vehicle is determined to be the parking state.
In the embodiment of the invention, if the obtained plurality of continuous GPS point data are GPS point data in a GPS point data set trained by an ETA model, and after the obtained plurality of continuous GPS point data are processed according to the method, and the driving state of the vehicle is determined to be the parking state, the obtained plurality of continuous GPS point data can be removed from the GPS point data set trained by the ETA model, in the specific practical process, the GPS point data corresponding to the parking state has influence on an ETA result trained by the ETA model, therefore, the GPS point data corresponding to the parking state is considered as a vehicle driving track of abnormal behavior, so abnormal data in the ETA model can be removed through the invention, the ETA model can obtain more reliable training data without containing abnormality during model training, and simultaneously, more reliable evaluation results can be obtained by using the more reliable data during the evaluation of the ETA model, the iteration of the ETA model is purposeful, and the ETA result is more accurate.
Based on the same inventive concept, an embodiment of the present invention provides an apparatus for identifying a vehicle driving state, where for specific implementation of a method for identifying a vehicle driving state of the apparatus, reference may be made to the description of the above method embodiment, and repeated descriptions are omitted, and as shown in fig. 8, the apparatus includes:
an acquisition unit 40 for acquiring a plurality of consecutive GPS point data of the vehicle;
a first determining unit 41, configured to determine, according to the obtained GPS point data, a displacement direction vector between every two adjacent GPS points or between every two GPS points that are separated by a set number, and obtain a plurality of displacement direction vectors;
the second determining unit 42 is configured to determine, according to the plurality of displacement direction vectors, a displacement direction included angle between every two adjacent displacement direction vectors, so as to obtain a plurality of displacement direction included angles;
and a third determining unit 43, configured to determine a vehicle driving state according to a change characteristic of the plurality of displacement direction included angles during the driving process of the vehicle.
Optionally, the third determining unit is further configured to:
determining the variation range of the included angles of the plurality of displacement directions;
and determining the vehicle driving states according to the threshold value ranges of the variation ranges of the plurality of displacement direction included angles, wherein each vehicle driving state corresponds to one threshold value range.
Optionally, the third determining unit is further configured to:
determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain a plurality of displacement direction included angle cosine values;
determining a first-order difference of cosine values of included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences;
and determining the variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences.
Optionally, the third determining unit is further configured to:
determining a variance or standard deviation of the plurality of first-order differences, wherein the variance or standard deviation represents a variation range of the plurality of displacement direction included angles.
Optionally, the third determining unit is further configured to:
performing wavelet transformation on the first-order differences to obtain a wavelet transformation result, wherein the wavelet transformation result represents the variation range of the included angles of the displacement directions; or
And performing convolution on the plurality of first-order differences to obtain a convolution result, wherein the convolution result represents the variation range of the plurality of displacement direction included angles.
Optionally, the multiple continuous GPS point data are:
setting all GPS point data acquired within a time length; or
After all the GPS point data obtained over a period of time are divided into a plurality of sample groups in chronological order, a plurality of consecutive GPS point data included in any one sample group.
Optionally, the third determining unit is further configured to:
and if the difference of the displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is determined to be smaller than a second threshold value according to the acquired GPS point data, determining that the vehicle driving state is a parking state.
Optionally, the third determining unit is further configured to:
when the plurality of continuous GPS point data are obtained from the GPS point data set when the GPS point data set used for ETA model training is subjected to data preprocessing, and when the vehicle driving state is determined to be a parking state, the plurality of continuous GPS point data are removed from the GPS point data set.
Based on the same inventive concept, an embodiment of the present invention provides a computing device, as shown in fig. 9, comprising at least one processor 50, and at least one memory 51, wherein the memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the method for identifying a driving state of a vehicle as described above.
Based on the same inventive concept, embodiments of the present invention provide a computer-readable medium storing a computer program executable by a terminal device, which, when the program is run on the terminal device, causes the terminal device to perform the steps of the method for identifying a driving state of a vehicle as described above.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims (11)

1. A method of recognizing a driving state of a vehicle, characterized by comprising:
obtaining a plurality of continuous GPS point data of a vehicle;
determining displacement direction vectors between every two adjacent GPS points or between every two GPS points separated by a set number according to the obtained GPS point data to obtain a plurality of displacement direction vectors;
determining a displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles;
determining a vehicle driving state according to the change characteristics of the plurality of displacement direction included angles in the driving process of the vehicle, wherein the vehicle driving state comprises one of a normal driving state, a low-speed driving state and a parking state;
the determining the driving state of the vehicle according to the change characteristics of the plurality of displacement direction included angles in the driving process of the vehicle comprises the following steps:
determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain a plurality of displacement direction included angle cosine values;
determining a first-order difference of cosine values of included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences;
determining the variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences;
and determining the vehicle driving states according to the threshold value ranges of the variation ranges of the plurality of displacement direction included angles, wherein each vehicle driving state corresponds to one threshold value range.
2. The method according to claim 1, wherein the determining a variation range of the plurality of included angles of the displacement direction according to the discrete features of the plurality of first-order differences is specifically:
determining a variance or standard deviation of the plurality of first-order differences, wherein the variance or standard deviation represents a variation range of the plurality of displacement direction included angles.
3. The method according to claim 1, wherein the determining a variation range of the plurality of included angles of the displacement direction according to the discrete features of the plurality of first-order differences is specifically:
performing wavelet transformation on the first-order differences to obtain a wavelet transformation result, wherein the wavelet transformation result represents the variation range of the included angles of the displacement directions; or
And performing convolution on the plurality of first-order differences to obtain a convolution result, wherein the convolution result represents the variation range of the plurality of displacement direction included angles.
4. The method of claim 1, wherein the plurality of consecutive GPS point data is:
setting all GPS point data acquired within a time length; or
After all the GPS point data obtained over a period of time are divided into a plurality of sample groups in chronological order, a plurality of consecutive GPS point data included in any one sample group.
5. The method of any one of claims 1-4, wherein after obtaining a plurality of successive GPS point data for the vehicle, the method further comprises:
and if the difference of the displacement coordinates between two adjacent GPS points or between two GPS points separated by a set number is determined to be smaller than a second threshold value according to the acquired GPS point data, determining that the vehicle driving state is a parking state.
6. The method of any one of claims 1-4, further comprising:
when the plurality of continuous GPS point data are obtained from the GPS point data set when the data preprocessing is performed on the GPS point data set used for the ETA model training of the estimated arrival time, the plurality of continuous GPS point data are removed from the GPS point data set when the driving state of the vehicle is determined to be the parking state.
7. An apparatus for recognizing a driving state of a vehicle, comprising:
an acquisition unit for acquiring a plurality of continuous GPS point data of a vehicle;
the first determining unit is used for determining displacement direction vectors between every two adjacent GPS points or between every two GPS points which are separated by a set number according to the acquired GPS point data to obtain a plurality of displacement direction vectors;
the second determining unit is used for determining a displacement direction included angle of every two adjacent displacement direction vectors according to the plurality of displacement direction vectors to obtain a plurality of displacement direction included angles;
a third determining unit, configured to determine a vehicle driving state according to a change characteristic of the plurality of displacement direction included angles during driving of the vehicle, where the vehicle driving state includes one of a normal driving state, a low-speed driving state, and a parking state;
the third determining unit is specifically configured to:
determining cosine values of every two adjacent displacement direction included angles in the plurality of displacement direction included angles to obtain a plurality of displacement direction included angle cosine values;
determining a first-order difference of cosine values of included angles of every two adjacent displacement directions according to the cosine values of the included angles of the plurality of displacement directions to obtain a plurality of first-order differences;
determining the variation range of the included angles of the plurality of displacement directions according to the discrete features of the plurality of first-order differences;
and determining the vehicle driving states according to the threshold value ranges of the variation ranges of the plurality of displacement direction included angles, wherein each vehicle driving state corresponds to one threshold value range.
8. The identification apparatus of claim 7, wherein the third determination unit is further configured to:
determining a variance or standard deviation of the plurality of first-order differences, wherein the variance or standard deviation represents a variation range of the plurality of displacement direction included angles.
9. The identification apparatus of claim 7, wherein the third determination unit is further configured to:
performing wavelet transformation on the first-order differences to obtain a wavelet transformation result, wherein the wavelet transformation result represents the variation range of the included angles of the displacement directions; or
And performing convolution on the plurality of first-order differences to obtain a convolution result, wherein the convolution result represents the variation range of the plurality of displacement direction included angles.
10. A computing device comprising at least one processor and at least one memory, wherein the memory stores a computer program that, when executed by the processor, causes the processor to perform the steps of the method of any of claims 1 to 6.
11. A computer-readable medium, in which a computer program executable by a terminal device is stored, which program, when run on the terminal device, causes the terminal device to carry out the steps of the method according to any one of claims 1 to 6.
CN201810338511.2A 2018-04-16 2018-04-16 Vehicle driving state identification method and device and storage medium Active CN110161544B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810338511.2A CN110161544B (en) 2018-04-16 2018-04-16 Vehicle driving state identification method and device and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810338511.2A CN110161544B (en) 2018-04-16 2018-04-16 Vehicle driving state identification method and device and storage medium

Publications (2)

Publication Number Publication Date
CN110161544A CN110161544A (en) 2019-08-23
CN110161544B true CN110161544B (en) 2022-03-01

Family

ID=67644739

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810338511.2A Active CN110161544B (en) 2018-04-16 2018-04-16 Vehicle driving state identification method and device and storage medium

Country Status (1)

Country Link
CN (1) CN110161544B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112748451B (en) * 2021-01-26 2022-04-22 腾讯科技（深圳）有限公司 Track processing method and device, electronic equipment and medium

Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103018754A (en) * 2012-11-29 2013-04-03 无锡坦程物联网科技有限公司 Turning distinguishing method based on GPS (Global Position System) data
CN103697897A (en) * 2013-12-06 2014-04-02 成都亿盟恒信科技有限公司 Inflection point compensation of vehicle track information
KR20140065642A (en) * 2012-11-19 2014-05-30 한국전자통신연구원 Apparatus and method for determining traveling status of vehicle
CN104658255A (en) * 2015-03-10 2015-05-27 北京嘀嘀无限科技发展有限公司 Method and device for detecting stationary vehicle state based on GPS data
JP2016018304A (en) * 2014-07-07 2016-02-01 株式会社デンソーアイティーラボラトリ Safety confirmation determination device and drive assist device
CN105741537A (en) * 2016-03-29 2016-07-06 福建工程学院 Vehicle passenger-seeking state identification method and system
CN105957183A (en) * 2016-04-21 2016-09-21 深圳市元征科技股份有限公司 Detection method and apparatus for stationary state of vehicle
CN106127883A (en) * 2016-06-23 2016-11-16 北京航空航天大学 driving event detection method
CN106530789A (en) * 2016-10-31 2017-03-22 成都路行通信息技术有限公司 Automobile parking point static drift detection method and system
CN106548630A (en) * 2017-01-11 2017-03-29 青岛海信移动通信技术股份有限公司 A kind of detection method and device of driving behavior
CN106814700A (en) * 2015-11-30 2017-06-09 沈阳高精数控智能技术股份有限公司 A kind of small line segment connection speed computational methods of numerical control device individual axis acceleration constraint
CN107037473A (en) * 2017-04-07 2017-08-11 南京人人保网络技术有限公司 Zig zag driving behavior recognition methods and device based on mobile device

Patent Citations (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20140065642A (en) * 2012-11-19 2014-05-30 한국전자통신연구원 Apparatus and method for determining traveling status of vehicle
CN103018754A (en) * 2012-11-29 2013-04-03 无锡坦程物联网科技有限公司 Turning distinguishing method based on GPS (Global Position System) data
CN103697897A (en) * 2013-12-06 2014-04-02 成都亿盟恒信科技有限公司 Inflection point compensation of vehicle track information
JP2016018304A (en) * 2014-07-07 2016-02-01 株式会社デンソーアイティーラボラトリ Safety confirmation determination device and drive assist device
CN104658255A (en) * 2015-03-10 2015-05-27 北京嘀嘀无限科技发展有限公司 Method and device for detecting stationary vehicle state based on GPS data
CN106814700A (en) * 2015-11-30 2017-06-09 沈阳高精数控智能技术股份有限公司 A kind of small line segment connection speed computational methods of numerical control device individual axis acceleration constraint
CN105741537A (en) * 2016-03-29 2016-07-06 福建工程学院 Vehicle passenger-seeking state identification method and system
CN105957183A (en) * 2016-04-21 2016-09-21 深圳市元征科技股份有限公司 Detection method and apparatus for stationary state of vehicle
CN106127883A (en) * 2016-06-23 2016-11-16 北京航空航天大学 driving event detection method
CN106530789A (en) * 2016-10-31 2017-03-22 成都路行通信息技术有限公司 Automobile parking point static drift detection method and system
CN106548630A (en) * 2017-01-11 2017-03-29 青岛海信移动通信技术股份有限公司 A kind of detection method and device of driving behavior
CN107037473A (en) * 2017-04-07 2017-08-11 南京人人保网络技术有限公司 Zig zag driving behavior recognition methods and device based on mobile device

Also Published As

Publication number Publication date
CN110161544A (en) 2019-08-23

Similar Documents

Publication Publication Date Title
CN107657637B (en) Method for acquiring operation area of agricultural machine
US9170115B2 (en) Method and system for generating road map using data of position sensor of vehicle
CN111179589B (en) Method, device, equipment and storage medium for predicting vehicle OD
CN109507699B (en) Satellite positioning correction method and device for vehicle
US11227487B2 (en) Server device and congestion identification method
JP6460474B2 (en) Traffic event estimation device, traffic event estimation system, traffic event estimation method, and computer program
CN103578272A (en) Method and device for recognizing abnormal road conditions
CN112885099B (en) Method, device and equipment for determining key points of vehicle track
CN111060153B (en) Method and device for detecting cargo state of truck and storage medium
CN104395944A (en) Carriageway recognition
JP2019519041A (en) Method, apparatus and system for detecting reverse running driver
WO2023034141A1 (en) System and method for monitoring a vehicle
CN103971519A (en) System and method of using traffic conflicts for judging accident-prone sections
CN110161544B (en) Vehicle driving state identification method and device and storage medium
CN107221183B (en) real-time station reporting method and device for public transport means
CN106528553B (en) A kind of train signal processing method and processing device
CN102436742A (en) Method and device for evaluating traffic information service level of floating vehicle system
US20190088117A1 (en) Traffic volume determination system, traffic volume determination method, and non-transitory computer-readable storage medium storing traffic volume determination program
CN113324560A (en) Method, system and computer readable medium for obtaining vehicle mileage
CN111739291B (en) Interference identification method and device in road condition calculation
CN115995151B (en) Network vehicle-closing abnormal behavior detection method applied to city management
CN103714701B (en) A kind of method that complexity circuit quickly judges hypervelocity
US10618524B2 (en) Method for determining a reference driving class
CN110718070A (en) Accompanying vehicle identification method, device, equipment and storage medium
CN111488417A (en) Information processing method, system, device, equipment and computer storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant